本文整理汇总了Python中tensorflow.compat.v1.sqrt方法的典型用法代码示例。如果您正苦于以下问题:Python v1.sqrt方法的具体用法?Python v1.sqrt怎么用?Python v1.sqrt使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.compat.v1
的用法示例。
在下文中一共展示了v1.sqrt方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _make_update
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def _make_update(self):
mss = []
gsum = 0.0
count = 0
for sum_squared_grads in self._sum_squared_grads:
ms = tf.sqrt(sum_squared_grads / self._num_squared_grads)
gsum += tf.reduce_sum(ms)
count += tf.reduce_sum(tf.ones_like(ms))
mss.append(ms)
gsum = gsum / count
assignments = []
for grad, var, save, sum_squared_grads, ms in zip(
self._grads, self._vars, self._saves, self._sum_squared_grads, mss):
decay_rate = tf.minimum(1.0, self._decay_rate*(ms/gsum))
delta = (-self._learning_rate*grad / (ms + self._epsilon) +
decay_rate*(save-var))
assignments.append(var.assign_add(delta))
return tf.group(assignments)
示例2: layer_norm
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def layer_norm(x, reduction_indices, epsilon=1e-9, gain=None, bias=None,
per_element=True, scope=None):
"""DOC."""
reduction_indices = ensure_list(reduction_indices)
mean = tf.reduce_mean(x, reduction_indices, keep_dims=True)
variance = tf.reduce_mean(tf.squared_difference(x, mean),
reduction_indices, keep_dims=True)
normalized = (x - mean) / tf.sqrt(variance + epsilon)
dtype = x.dtype
shape = x.get_shape().as_list()
for i in six.moves.range(len(shape)):
if i not in reduction_indices or not per_element:
shape[i] = 1
with tf.variable_scope(scope or 'layer_norm'):
if gain is None:
gain = tf.get_variable('gain', shape=shape, dtype=dtype,
initializer=tf.ones_initializer())
if bias is None:
bias = tf.get_variable('bias', shape=shape, dtype=dtype,
initializer=tf.zeros_initializer())
return gain*normalized+bias
示例3: _dist_to_opt
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def _dist_to_opt(self):
"""Distance to optimum.
Returns:
D_t ops
"""
dist_to_opt_ops = []
# Running average of the norm of gradient
self._grad_norm = tf.sqrt(self._grad_norm_squared)
avg_op = self._moving_averager.apply([self._grad_norm,])
dist_to_opt_ops.append(avg_op)
with tf.control_dependencies([avg_op]):
self._grad_norm_avg = self._moving_averager.average(self._grad_norm)
# Single iteration distance estimation, note here
# self._grad_norm_avg is per variable
self._d_t = self._grad_norm_avg / self._grad_norm_squared_avg
# Running average of distance
avg_op = self._moving_averager.apply([self._d_t])
dist_to_opt_ops.append(avg_op)
with tf.control_dependencies([avg_op]):
self._dist_to_opt_avg = tf.identity(
self._moving_averager.average(self._d_t))
if self._sparsity_debias:
self._dist_to_opt_avg /= tf.sqrt(self._sparsity_avg)
return dist_to_opt_ops # D_t
示例4: _grad_sparsity
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def _grad_sparsity(self):
"""Gradient sparsity."""
# If the sparse minibatch gradient has 10 percent of its entries
# non-zero, its sparsity is 0.1.
# The norm of dense gradient averaged from full dataset
# are roughly estimated norm of minibatch
# sparse gradient norm * sqrt(sparsity)
# An extension maybe only correct the sparse blob.
non_zero_cnt = tf.add_n([tf.count_nonzero(g) for g in self._grad])
all_entry_cnt = tf.add_n([tf.size(g) for g in self._grad])
self._sparsity = tf.cast(non_zero_cnt, self._grad[0].dtype)
self._sparsity /= tf.cast(all_entry_cnt, self._grad[0].dtype)
avg_op = self._moving_averager.apply([self._sparsity,])
with tf.control_dependencies([avg_op]):
self._sparsity_avg = self._moving_averager.average(self._sparsity)
return avg_op
示例5: xception_exit
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def xception_exit(inputs):
"""Xception exit flow."""
with tf.variable_scope("xception_exit"):
x = inputs
x_shape = x.get_shape().as_list()
if x_shape[1] is None or x_shape[2] is None:
length_float = tf.to_float(tf.shape(x)[1])
length_float *= tf.to_float(tf.shape(x)[2])
spatial_dim_float = tf.sqrt(length_float)
spatial_dim = tf.to_int32(spatial_dim_float)
x_depth = x_shape[3]
x = tf.reshape(x, [-1, spatial_dim, spatial_dim, x_depth])
elif x_shape[1] != x_shape[2]:
spatial_dim = int(math.sqrt(float(x_shape[1] * x_shape[2])))
if spatial_dim * spatial_dim != x_shape[1] * x_shape[2]:
raise ValueError("Assumed inputs were square-able but they were "
"not. Shape: %s" % x_shape)
x = tf.reshape(x, [-1, spatial_dim, spatial_dim, x_depth])
x = common_layers.conv_block_downsample(x, (3, 3), (2, 2), "SAME")
return tf.nn.relu(x)
示例6: _data_dep_init
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def _data_dep_init(self, inputs):
"""Data dependent initialization for eager execution."""
with tf.variable_scope("data_dep_init"):
# Generate data dependent init values
activation = self.layer.activation
self.layer.activation = None
x_init = self.layer.call(inputs)
m_init, v_init = tf.moments(x_init, self.norm_axes)
scale_init = 1. / tf.sqrt(v_init + 1e-10)
# Assign data dependent init values
self.layer.g = self.layer.g * scale_init
self.layer.bias = (-m_init * scale_init)
self.layer.activation = activation
self.initialized = True
示例7: dense_weightnorm
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def dense_weightnorm(
name, x, n_out, x_mask, init_scale, init, dtype=tf.float32):
"""Dense layer with weight normalization."""
n_in = common_layers.shape_list(x)[2]
eps = tf.keras.backend.epsilon()
with tf.variable_scope(name, reuse=tf.AUTO_REUSE):
v = tf.get_variable(
"v", [n_in, n_out], dtype,
initializer=tf.random_normal_initializer(0, 0.05), trainable=True)
v = v / tf.norm(v, axis=0, keepdims=True)
t = tf.matmul(x, v) # [B, L, n_out]
mean, var = moments_over_bl(t, x_mask)
g_init = init_scale / (tf.sqrt(var) + eps)
g = get_variable_ddi(
"g", [n_out], g_init, init,
initializer=tf.zeros_initializer, dtype=dtype, trainable=True)
b = get_variable_ddi(
"b", [n_out], -mean*g_init, init,
initializer=tf.zeros_initializer, dtype=dtype, trainable=True)
w = g * v
y = tf.matmul(x, w) + b
tf.summary.histogram("_g", g)
return y
示例8: test_group_lasso_conv3d
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def test_group_lasso_conv3d(self):
shape = [3, 3, 3]
video = tf.zeros([2, 3, 3, 3, 1])
net = slim.conv3d(
video,
5,
shape,
padding='VALID',
weights_initializer=tf.glorot_normal_initializer(),
scope='vconv1')
conv3d_op = tf.get_default_graph().get_operation_by_name('vconv1/Conv3D')
conv3d_weights = conv3d_op.inputs[1]
threshold = 0.09
flop_reg = flop_regularizer.GroupLassoFlopsRegularizer([net.op],
threshold=threshold)
norm = tf.sqrt(tf.reduce_mean(tf.square(conv3d_weights), [0, 1, 2, 3]))
alive = tf.reduce_sum(tf.cast(norm > threshold, tf.float32))
with self.session():
flop_coeff = 2 * shape[0] * shape[1] * shape[2]
tf.compat.v1.global_variables_initializer().run()
self.assertAllClose(flop_reg.get_cost(), flop_coeff * alive)
self.assertAllClose(flop_reg.get_regularization_term(),
flop_coeff * tf.reduce_sum(norm))
示例9: __init__
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def __init__(self, regularizers_to_group, threshold=DEFAULT_THRESHOLD):
"""Creates an instance.
Args:
regularizers_to_group: A list of generic_regularizers.OpRegularizer
objects.Their regularization_vector (alive_vector) are expected to be of
the same length.
threshold: A float. An group of activations will be considered alive if
its L2 norm is greater than `threshold`.
Raises:
ValueError: regularizers_to_group is not of length at least 2.
"""
if len(regularizers_to_group) < 2:
raise ValueError('Groups must be of at least size 2.')
self._regularization_vector = tf.sqrt(
tf.add_n([
lazy_square(r.regularization_vector)
for r in regularizers_to_group
]))
self._alive_vector = self._regularization_vector > threshold
示例10: lazy_square
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def lazy_square(tensor):
"""Computes the square of a tensor in a lazy way.
This function is lazy in the following sense, for:
tensor = tf.sqrt(input)
will return input (and not tf.square(tensor)).
Args:
tensor: A `Tensor` of floats to compute the square of.
Returns:
The square of the input tensor.
"""
if tensor.op.type == 'Sqrt':
return tensor.op.inputs[0]
else:
return tf.square(tensor)
示例11: _apply_gradients
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def _apply_gradients(self, grads, x, optim_state):
"""Applies gradients."""
lr = self._lr_fn(optim_state.t)
new_optim_state = self._State(
t=optim_state.t + 1,
m=[None] * len(x),
u=[None] * len(x))
t = tf.cast(new_optim_state.t, tf.float32)
new_x = [None] * len(x)
for i in range(len(x)):
g = grads[i]
m_old = optim_state.m[i]
u_old = optim_state.u[i]
new_optim_state.m[i] = self._beta1 * m_old + (1. - self._beta1) * g
new_optim_state.u[i] = self._beta2 * u_old + (1. - self._beta2) * g * g
m_hat = new_optim_state.m[i] / (1. - tf.pow(self._beta1, t))
u_hat = new_optim_state.u[i] / (1. - tf.pow(self._beta2, t))
new_x[i] = x[i] - lr * m_hat / (tf.sqrt(u_hat) + self._epsilon)
return new_x, new_optim_state
示例12: layer_norm
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def layer_norm(layer_inputs, hidden_size):
"""Implements layer norm from [Ba et al. 2016] Layer Normalization.
See eqn. 4 in (https://arxiv.org/pdf/1607.06450.pdf).
Args:
layer_inputs (tensor): The inputs to the layer.
shape <float32>[batch_size, hidden_size]
hidden_size (int): Dimensionality of the hidden layer.
Returns:
normalized (tensor): layer_inputs, normalized over all the hidden units in
the layer.
shape <float32>[batch_size, hidden_size]
"""
mean, var = tf.nn.moments(layer_inputs, [1], keep_dims=True)
with tf.variable_scope("layernorm", reuse=tf.AUTO_REUSE):
gain = tf.get_variable(
"gain", shape=[hidden_size], initializer=tf.constant_initializer(1))
bias = tf.get_variable(
"bias", shape=[hidden_size], initializer=tf.constant_initializer(0))
normalized = gain * (layer_inputs - mean) / tf.sqrt(var + _EPSILON) + bias
return normalized
示例13: normalized_mean_square_error
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def normalized_mean_square_error(output, target):
"""Return the TensorFlow expression of normalized mean-squre-error of two distributions.
Parameters
----------
output : 2D or 4D tensor.
target : 2D or 4D tensor.
"""
with tf.name_scope("mean_squared_error_loss"):
if output.get_shape().ndims == 2: # [batch_size, n_feature]
nmse_a = tf.sqrt(tf.reduce_sum(tf.squared_difference(output, target), axis=1))
nmse_b = tf.sqrt(tf.reduce_sum(tf.square(target), axis=1))
elif output.get_shape().ndims == 4: # [batch_size, w, h, c]
nmse_a = tf.sqrt(tf.reduce_sum(tf.squared_difference(output, target), axis=[1,2,3]))
nmse_b = tf.sqrt(tf.reduce_sum(tf.square(target), axis=[1,2,3]))
nmse = tf.reduce_mean(nmse_a / nmse_b)
return nmse
示例14: cosine_similarity
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def cosine_similarity(v1, v2):
"""Cosine similarity [-1, 1], `wiki <https://en.wikipedia.org/wiki/Cosine_similarity>`_.
Parameters
-----------
v1, v2 : tensor of [batch_size, n_feature], with the same number of features.
Returns
-----------
a tensor of [batch_size, ]
"""
try: ## TF1.0
cost = tf.reduce_sum(tf.multiply(v1, v2), 1) / (tf.sqrt(tf.reduce_sum(tf.multiply(v1, v1), 1)) * tf.sqrt(tf.reduce_sum(tf.multiply(v2, v2), 1)))
except: ## TF0.12
cost = tf.reduce_sum(tf.mul(v1, v2), reduction_indices=1) / (tf.sqrt(tf.reduce_sum(tf.mul(v1, v1), reduction_indices=1)) * tf.sqrt(tf.reduce_sum(tf.mul(v2, v2), reduction_indices=1)))
return cost
## Regularization Functions
示例15: _ensure_keep_mask
# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import sqrt [as 别名]
def _ensure_keep_mask(self, x):
if self._keep_mask is None or not self._share_mask:
shape = tf.shape(x)
# Calculate the stddev for the normal distribution that
# matches the stddev of the bernoulli with p=keep_prob.
stddev = tf.sqrt((1 - self._keep_prob) / self._keep_prob)
self._keep_mask = tf.random_normal(shape, mean=1.0, stddev=stddev,
dtype=x.dtype)
self._keep_mask.set_shape(x.get_shape())
return self._keep_mask